Hermes Agent dominates the week: OpenClaw in direct comparison and security vulnerabilities in focus
Thursday, May 14, 2026
Hello, this weekly newsletter guides you through the most important new videos from a curated selection of AI and coding YouTube channels. Each video gets a compact summary, plus a daily overview of the dominant topics. If interested, simply click the link under the summary.
The week was characterized by intense comparisons between the AI agents Hermes and OpenClaw, which were thoroughly tested and discussed in several videos by Alex Finn. The “Agent Olympics” showed that OpenClaw with Opus often came out ahead in various task areas such as infographic creation and animated music videos. Hermes, on the other hand, was criticized for its instability and “compaction” errors, which led to loss of work states. Nevertheless, Finn emphasized the advantages of Hermes, particularly its reliability and user-friendliness, and recommended its use for productivity-enhancing workflows.
Another central topic was a security vulnerability in the Linux kernel, discovered by an AI tool. Fireship explained in detail how the vulnerability could be exploited and why urgent updates are necessary. This underscores the growing importance of AI tools in discovering and fixing security risks. Beyond these technical topics, there were also personal insights from Alex Finn, who spoke about his sleep problems and work methods, making the videos even more vivid and relatable for viewers.
An outlier this week was Fireship’s video on operating systems, which provided a comprehensive overview of how operating systems work from the boot phase to shutdown. This video was more technical in nature and targets intermediate or advanced viewers seeking a deeper understanding of fundamental operating system concepts. Overall, the week showed a strong focus on AI agents and their comparison, as well as on security aspects and fundamental technical concepts.
Niklas Steenfatt
No new videos in this period.
Fireship (2 new videos)
- Every operating system concept in one video…
7.5.2026, 17:32:34The video explains in detail how an operating system functions from the moment you press the power button until shutdown. It starts with the bootloader, which loads the operating system, then moves on to privilege rings, which separate kernel rights from application rights. Virtual memory is described as a system that enables multiple applications to run in parallel without interfering with each other. The kernel sets up the file system, loads device drivers, and enables interrupts, which allow the system to respond to input. The kernel then starts the first process (PID1), which is the ancestor of all other processes. System calls enable applications to communicate with the kernel, and the scheduler manages CPU time across many processes. Threads allow applications to perform multiple tasks simultaneously, and interprocess communication (IPC) enables different processes to communicate safely. Finally, the shutdown process is described, where all processes are terminated and the system shuts down safely.
The video generally covers operating systems and their components without mentioning specific tools or vendors, and is better suited for intermediate or advanced viewers.
- 732 bytes of Python just borked every Linux machine on earth…
4.5.2026, 18:40:40The video covers a critical security vulnerability in the Linux kernel, referred to as “copy fail” (CVE-2023-31431), which has existed since 2017 and was discovered by an AI tool. The vulnerability allows a local user to gain root access by writing four bytes into the page cache of a read-only file. All Linux distributions updated after 2017 are affected. The vulnerability was exploited using a Python script that leverages the ONC ESN protocol and the AF_AGL interface. Although the vulnerability is not remotely exploitable, updating systems is strongly recommended. The video also mentions the role of AI in discovering security vulnerabilities and promotes Code Rabbit, an AI tool for improving code quality.
The video explicitly covers AI tools such as the AI agent tool used by Theori and Code Rabbit, and is intended for intermediate to advanced users.
Alex Finn (8 new videos)
- LIVE: The greatest Claude Code workflow ever
13.5.2026, 20:12:33The video showcases a detailed, advanced workflow for Claude Code that integrates various tools like Slack, Linear, GitHub, and Claude Code. The host explains how these tools work together to boost productivity, track changes, and organize development. The workflow includes creating tasks and projects in Linear, linking with GitHub for branch management, and using Claude Code for automating and managing these processes. The host emphasizes the benefits of this workflow, such as increased speed, better error prevention, and improved traceability.
Additionally, the host discusses personal experiences and challenges, such as dealing with difficult times and the importance of perseverance. He also shares his thoughts on using AI tools like Claude Code and Codex, as well as their differences and use cases.
The video is aimed at advanced users who already have experience with Claude Code and similar tools and want to optimize their workflows. Specific tools like Claude, OpenAI, and Linear are addressed.
- Hermes Agent powered by local models on the DGX Spark is basically magic
13.5.2026, 13:30:07The video demonstrates how to set up a Hermes Agent on a local model on an Nvidia DGX Spark to create a 24/7 available AI coworker. The process includes setting up the DGX Spark in headless mode, installing a local model (Quen 3.6 27B), and integrating the model into the Hermes Agent. The creator demonstrates three use cases: a daily report on AI stocks for beginners, repurposing YouTube video content for advanced users, and vibe-coding a to-do list app for advanced users. The focus is on the benefits of local models, such as cost-free operation (apart from electricity), privacy, customizability, and educational value.
Closing comment: The video explicitly addresses Nvidia DGX Spark, Hermes Agent, Quen 3.6 27B, and Tail Scale and is intended for intermediate to advanced users.
- LIVE: Talking AI news (no Hermes use cases ignore the thumbnail)
11.5.2026, 20:11:47The video is a live stream session that primarily revolves around discussing Hermes Agent and its use cases. The host, Alex Finn, begins with an introduction to Hermes Agent and emphasizes the importance of use cases for leveraging the technology. He mentions that Hermes has launched a new website with hundreds of use cases that he and the viewers will go through and test.
However, much of the video is taken up by various tangents and discussions, including:
1. **Investment Corner**: Alex talks about current investment opportunities in the AI industry, particularly in companies like Nvidia, Micron, TSMC, and Tesla. He emphasizes the importance of current AI developments and the need to invest in the right companies.
2. **Personal Stories and Anecdotes**: Alex shares personal stories and anecdotes that are often humorous and entertaining but not directly related to the main topic of the video.
3. **Chat Interaction**: Much of the video consists of interaction with the live chat, where Alex answers questions, makes comments, and engages with viewers.
4. **Hermes Agent Use Cases**: Towards the end of the video, Alex begins discussing some of the use cases from the new Hermes website. He mentions use cases such as creating research reports, managing tasks, and automating processes.
5. **Announcements and Updates**: Alex provides updates on his own projects and announcements, such as launching a second YouTube channel and attending a Baby Keem concert.
**Closing Comment**: The video explicitly addresses open-source AI models and tools like Hermes Agent and OpenClaw. It is aimed more at intermediate to advanced users who already have some understanding of AI and its applications.
- Hermes Agent is blowing me away…
9.5.2026, 20:54:26The video compares the AI agents Hermes and OpenClaw, recommending Hermes due to its reliability, self-improvement capabilities, and user-friendliness. The author describes the benefits of Hermes, including regular thematic updates, self-improving abilities through usage, and a strong emphasis on experimentation and local models. Installing Hermes is described as straightforward, with options for different models and communication services, with Telegram and Opus recommended. The author showcases three use cases: one for beginners discovering new AI tools daily, one for advanced users performing daily proactive check-ins, and one for experts creating AI-generated videos. The author emphasizes the importance of brain-dumping and reverse-prompting to use the AI agent in a personal and effective manner.
The video explicitly addresses the AI tools Hermes Agent and OpenClaw and is aimed more at intermediate and advanced users.
- LIVE: Anthropic and Elon just teamed up to take down OpenAI
6.5.2026, 20:12:34The video covers the strategic alliance between Anthropic and Elon Musk’s XAI (X.AI), characterized by a major computing power deal. Anthropic gains access to SpaceX’s Colossus-1 cluster, which will significantly enhance their ability to develop and train AI models. This partnership marks a turning point in competition with OpenAI, which has held a dominant position in recent months with Codeex. During this time, Anthropic struggled with declining limits and less powerful models, which the new alliance aims to address. Elon Musk, who was previously critical of Anthropic, now provides massive computing resources, changing the dynamics of AI competition. The video also discusses Elon Musk’s long-term strategies, which may focus on bigger goals like autonomous vehicles, space exploration, and robotics, rather than staying in the AI chatbot competition. The alliance could lead to a new era of innovation and improvement in AI tools, benefiting consumers. The video emphasizes the importance of using both leading AI tools, Claude Code and Codeex, to benefit from their respective strengths.
**AI Tools/Models/Providers:** Anthropic, OpenAI, Elon Musk (X.AI), Claude, Codeex, Grock, Gemini, Open-Source
**Target Audience:** Intermediate - Hermes Agent might have just killed OpenClaw
5.5.2026, 21:11:59The video presents Hermes Agent as a more reliable alternative to OpenClaw and discusses seven new features that improve productivity and user-friendliness. These include:
1. **Cananband Board**: Enables multitasking through parallel processing of multiple task threads. A manager agent fills tasks with details and moves them through various statuses (Triage, To-Do, Ready, In Progress, Block, Done).
2. **Slashgo**: A high-level mission feature that assigns long-term tasks to the agent that can be worked on over an extended period. The quality of the prompt is crucial for good results.
3. **Profiles (Multi-Agents)**: Allows the creation of multiple agents with their own memories and capabilities to optimize performance and prevent overload.
4. **Model Catalog**: Simplifies switching and assigning models to specific tasks, improving cost control and efficiency.
5. **Compression**: By adjusting the compression threshold to 0.5, less drastic compressions are performed, improving memory capability.
6. **Curator Feature**: Automatically prunes rarely used skills every seven days to reduce bloat and maintain performance.
The video criticizes OpenClaw for frequent updates that lead to instability and performance issues, and highlights Hermes’ targeted, reliable updates. It recommends leveraging Hermes’ new features to boost productivity.
**Closing Comment**: The video explicitly addresses Hermes Agent and OpenClaw and is aimed more at intermediate to advanced users.
- LIVE: Is Hermes better than OpenClaw? FINALE!!!
4.5.2026, 21:53:53The YouTube video shows a live stream in which the host tests various AI agents (OpenClaw and Hermes) in a competition called “Agent Olympics.” The stream is unusually long (3.5 hours) and is divided into different segments ranging from technical tests to personal discussions to spontaneous decisions.
**Content Summary:**
1. **Agent Olympics:**
– The host tests four combinations of AI agents (OpenClaw and Hermes with different backend models like ChatGPT and Opus) on five different tasks.
– The tasks include creating infographics, animated music videos, and other complex projects.
– Results are evaluated live, with OpenClaw with Opus emerging as the winner in the end.2. **Technical Discussions:**
– There are detailed discussions about the stability and reliability of various AI agents, particularly Hermes, which is criticized for “compaction” errors (loss of work state).
– OpenClaw is praised for its consistency and user-friendliness.3. **Personal Topics:**
– The host discusses his sleep issues and experiments with various solutions like kiwis and magnesium.
– There are discussions about work methods, including the use of treadmills and standing desks, with the host expressing his preferences and dislikes.4. **Community Interaction:**
– Viewers are actively engaged in the chat, asking questions and providing feedback.
– The host spontaneously decides to create a second YouTube channel called “Alex Finn Labs,” leading to entertaining interaction with a viewer who had already reserved the desired channel name.5. **Announcements and Future Plans:**
– The host announces plans to publish more videos about Hermes and multi-agent setups in the future.
– It is discussed whether live streams should be held at later times to reach a broader audience.**Closing Comment:**
The video explicitly addresses the AI tools OpenClaw, Hermes, ChatGPT, and Opus. It is aimed more at intermediate and advanced users as it covers technical details and advanced applications of AI agents. - LIVE: OpenClaw vs Hermes Agent: The ultimate showdown
1.5.2026, 20:48:54The YouTube video shows a live stream in which various AI agents are tested in a direct comparison. The main participants are OpenClaw and Hermes, each running with the models ChatGPT and Opus. The stream is divided into several tests that evaluate the capabilities of the agents in different task areas.
1. **Test 1: Real-time Stock Dashboard**
– **OpenClaw with ChatGPT**: Fastest completion, but with an unattractive user interface (UI). The functionality was rated as solid.
– **Hermes with ChatGPT**: Slower and crashed the computer, resulting in a poor rating.
– **OpenClaw with Opus**: Slower than the ChatGPT version, but with a slightly better UI and additional features like Trading View integration.
– **Hermes with Opus**: Best UI and functionality, but slower than OpenClaw with ChatGPT.2. **Test 2: Game Development**
– **OpenClaw with ChatGPT**: Fast, but unplayable game.
– **OpenClaw with Opus**: Playable, but not particularly entertaining.
– **Hermes with ChatGPT**: Unplayable and graphically poor.
– **Hermes with Opus**: Best graphics and playability, rated as actually entertaining.3. **Test 3: Website Recreation (Apple.com)**
– **Hermes with Opus**: First completion, but below-average accuracy.
– **OpenClaw with Opus**: Better than Hermes with Opus, but not perfect.
– **OpenClaw with ChatGPT**: Most accurate, nearly perfect.
– **Hermes with ChatGPT**: Perfect recreation via screenshots, but ethically questionable.The stream concludes with Hermes with Opus in the lead, followed by OpenClaw with Opus and OpenClaw with ChatGPT. Hermes with ChatGPT falls significantly behind. The remaining tests will continue in the next live stream.
**Closing Comment**: The video explicitly addresses the AI models Claude (Opus), OpenAI (ChatGPT), and specific tools like OpenClaw and Hermes. It is aimed more at intermediate and advanced users interested in the performance and comparison of AI agents.
Leon van Zyl (9 new videos)
- Claude Code Agent View: Parallel Agents Are Here
14.5.2026, 10:51:58The video reports on a severe supply chain attack on open-source packages in the npm ecosystem, compromising over 100 packages with a combined download rate of more than 50 million per week. The attack exploited a vulnerability in Tanstack’s release process when an attacker created a pull request in a fork of the repository, triggering the CI/CD workflow. Using the `pull_request_target` option in the GitHub Actions workflow, the attacker was able to inject malicious code into the shared cache of the CI server. Later, this malicious code used a valid npm publish token to release compromised packages. The malware spread further by searching for additional npm publish tokens and using them to infect more packages. Affected companies included Mistral AI, UiPath, and Open Search. The malware deeply integrated into developer environments like VS Code and implemented a “dead man switch” that deleted the root directory of the affected system when cleanup was detected.
To protect against such attacks, the video recommends using PNPM version 1 or higher, which offers features like `minimum release age`, `block exotic subdependencies`, and `approved builds`. These features can help prevent malware spread by blocking newly released packages, preventing exotic dependencies, and allowing installation scripts only for trusted packages. The video explicitly addresses open-source tools and providers such as npm, GitHub Actions, and PNPM, and is aimed at intermediate to advanced users.
- Codex CLI Tutorial: Build an AI Image Studio from Scratch
11.5.2026, 11:17:21This video walks through building an AI image studio from scratch for creating YouTube thumbnails, posters, banners, and other graphic content. The process starts with setting up a Next.js project using the Codex CLI tool, which is based on GPT-5.5 and high reasoning levels. A database is set up with Docker and Postgres, and necessary tables for user authentication are migrated.
The focus is on creating a user-friendly interface that allows users to upload reference images, write prompts, and generate images. The developer leverages the Codex tool’s capabilities to design and test the user interface while adhering to a predefined design system. After designing the interface, the actual functionality is implemented using the OpenAI API key to access the GPT-4 image model. The developer shows how to upload reference images and assets and how to generate thumbnails that combine these elements.
At the end, the user interface is adjusted to ensure image generation only occurs through the dashboard rather than the homepage. The homepage is redesigned with a generated image and marketing text. The video emphasizes the efficiency and time savings achieved through using Codex and OpenAI, while noting the token limitations of the ChatGPT Plus plan.
The video explicitly addresses OpenAI (GPT-5.5, GPT-4 image model) and Codex. It is aimed at intermediate and advanced users as it covers advanced concepts such as Docker, Postgres, Next.js, and API integration.
- Create Custom OpenCode Agents #Shorts #OpenCode #AICoding
10.5.2026, 07:00:16The video demonstrates how to create custom agents in OpenCode. By default, there are two agents: “build” and “plan”. To create a custom agent, you run the `opencode agent create` command in the terminal. You then provide a description of the agent, for example, that an agent named John only responds with emojis. After creation, you can use the spacebar to define which functions or tools the agent can access. You also choose the agent mode: either for primary and subordinate roles or only as a subordinate agent. The video demonstrates creating a subordinate agent named John and shows how the main agent delegates a task to John. You can track the work of the subordinate agent and see its reasoning and output. Finally, it emphasizes that this is just a demonstration and in practice you could use more specific system prompts and tool access for subordinate agents.
The video addresses OpenCode and is suitable for intermediate users.
- OpenCode’s Best Hidden Feature #Shorts #OpenCode #AICoding
9.5.2026, 07:00:19The video explains how to configure different models for different modes in OpenCode. For example, you can use a powerful model like GPT-5 for planning mode and a fast, cost-effective model like Big Pickle for implementation mode (Bold Mode). Alternatively, you can use GPT-5.5 for planning but reduce effort by selecting the “/variants” command with the “low effort” option. This allows planning to be created by an intelligent model while implementation can be handled by a less powerful but faster model.
The video addresses open-source models and is suitable for intermediate users.
- I Turned Hermes Agent Into a Coding Agent
8.5.2026, 11:02:33The video shows how to use Hermes Agent as a coding agent to create and deploy a web app online. The process includes setting up Hermes Agent on a VPS, integrating it with Telegram for communication, installing the Vercel CLI tool for deployment, and configuring the necessary skills for the agent. The creator tests whether the agent can create a personal portfolio page by scraping information from the creator’s YouTube channel and creating an appealing frontend design. The agent successfully creates the app, deploys it to Vercel, and provides a public URL that opens the app in a browser. The video also shows that the agent can make changes to the app and deploy them automatically.
The creator concludes that Hermes is suitable as a coding agent for simple tasks and quick dashboards, but not for complex software projects. The video explicitly addresses Hermes Agent, OpenAI Codex, GPT 5.5, Vercel, and Telegram. It is aimed at intermediate and advanced users.
- This free OpenCode trick saves thousands #opencode #aitools #hacks
7.5.2026, 13:38:39The video explains how to use free AI models for code generation in OpenCode. First, you run the “connect” command and search for “OpenCode Zen” under providers. Then you generate an API key through a provided URL, which is free. After entering the API key, you get a list of supported models including Big Pickle, HY3, Minimax M2.5, and Neurotron 3 Super from Nvidia. These models are powerful and completely free.
The video addresses OpenCode and OpenCode Zen and is aimed at intermediate users.
- I Built a Coding Agent That Runs Locally for Free
6.5.2026, 12:25:00The video introduces the open-source tool “Honeyfree,” which enables users to autonomously plan and implement software projects. The user describes what they want to build, and the tool plans the features, adds them to a Kanban board, and implements them automatically. The tool supports various models like Alum Studio and Ollama and can break down complex tasks into smaller features. The creator demonstrates building a simple to-do app and shows how to add and implement new features. The video emphasizes that this is now possible with free models, which wasn’t the case a few months ago. It also explains how to download models like Qwen 3.6 or JML4 and use them in Alum Studio or Llama Studio. The creator recommends increasing the context window length of models to at least 64,000 tokens for better performance. The video also shows how to install and set up Local Forge to create and manage projects. It notes that free models are good at writing code but require more detailed instructions for better results. The creator recommends using a paid model like Claude for planning features while using free models for actual implementation. The video ends with an invitation to sign up for a masterclass course teaching how to build applications with coding agents.
The video addresses open-source models like Qwen 3.6 and JML4, as well as tools like Alum Studio, Llama Studio, and Local Forge. It is suited for intermediate and advanced users who already have experience with AI models and software development.
- OpenCode Tutorial for Beginners: Setup, Agents, Skills & MCP
5.5.2026, 12:33:17The video is a tutorial showing how to create a Next.js application with OpenCode, an open-source AI tool. The process begins with installing and setting up OpenCode, including connecting to various AI models and providers, both free and paid. The tutorial demonstrates how to add agent capabilities such as frontend design and Next.js skills to improve the quality of generated code. It also shows how to use memory files and design systems to increase agent consistency and efficiency. The tutorial continues with creating an application that allows users to input a rough idea of their app and receive a detailed project plan. The agent uses subagents to execute tasks in parallel and protect the main context. At the end, the application is tested and refined, with the agent completely redesigning the UI and running automated tests. The video is suitable for intermediate and advanced users interested in AI-powered coding tools.
AI tools/models/providers: OpenCode (open-source), OpenAI, Anthropic, Gemini, OpenRouter, BigPikko, HY3, Minimax, Nvidia, Vercel, Cinta AI.
- I Built a Full App Using Only Cursor AI
4.5.2026, 11:01:35This video develops an AI-powered YouTube summarizer using the Cursor tool. The process begins with creating a user interface that takes a YouTube URL and delivers a video summary. Requirements include a short summary (TLDR), five to eight key points, a “Watch these moments” section with timestamps and descriptions, and the original video link.
The creator uses Cursor and decides on the Composer 2 model to scaffold the project. They install Next.js and the Shad cn library for the user interface. With Cursor’s agents, a basic user interface is created that meets the requirements. Next, functionality is added to retrieve the transcript of a YouTube video using the YouTube Transcript API.
For AI-powered summarization, the Cursor AI SDK is used to return structured data. The creator chooses the “anthropic/claude-2” model from OpenRouter and integrates the API key into an .env file. The agent then generates the summary, including the TLDR, key points, and recommended moments from the transcript.
The video explicitly addresses the tools Cursor, Composer 2, Next.js, Shad cn, YouTube Transcript API, AI SDK, and OpenRouter. It is suited for intermediate and advanced users.
Automatically generated from the latest YouTube videos of the curated channel selection. For feedback, suggestions, or to unsubscribe: simply reply to this email.